aj47

Browser automation using agent-browser CLI connected to a logged-in Chrome session via CDP. Use when asked to browse a website, fill forms, click buttons, take screenshots, scrape data, automate browser tasks, or any web interaction. Also use when asked to 'start chrome debugging', 'connect to chrome', or 'launch chrome for browser automation'.

Summarize X/Twitter feed quickly, including key links. Triggers: 'summarize my feed', 'what's on X', 'twitter summary', 'what's trending'

Posts tweets to X (Twitter) in AJ's voice. Use when asked to write a tweet, post to Twitter/X, compose a tweet, or share something on X. Handles both writing the tweet copy and posting it via browser automation.

Scrapes X/Twitter content from any profile or feed tab. Use when asked to scrape a specific Twitter user, get tweets from a profile, or extract X content beyond the Following feed.

Teaches the agent how to create new Agent Skills - the open standard for extending AI agent capabilities. Use this skill when asked to create, write, or develop new skills for AI agents.

Runs OpenAI Codex CLI agents in iTerm slots to work on GitHub issues. Use when asked to 'run codex on an issue', 'assign an issue to codex', 'spin up a codex agent', or 'have codex work on issue #N'.

Analyze video transcriptions to identify interesting segments for clipping. Finds highlights, key moments, and reactions with precise timestamps. Use when working with video transcriptions to extract clip-worthy moments. (project)

Process Twitch/YouTube stream transcripts to identify clip-worthy moments, generate short-form script notes, draft X posts, YouTube metadata, and extract content insights. Use when given a stream transcript, VOD URL, or when asked to find clips/highlights from a techfren stream.

Use this skill when the user asks to create, edit, or reason about a repeat task or loop — including phrases like 'create repeat task', 'recurring task', 'scheduled task', 'continuous task', 'same session continue', 'speak the result', 'TTS for a task', 'critique pass', or asks for good loop/cron prompt design. It teaches canonical task.md frontmatter, scheduler/runtime boundaries, prompt contracts, durable loop state, companion-skill factoring, and the safe edit workflow.

Use this skill when you need to inspect, change, or create DotAgents configuration. It teaches the canonical .agents file layout, layer precedence, and safe edit recipes for settings, models, MCP, prompts, agents, skills, tasks, and knowledge notes.

Teaches the agent how to create new Agent Skills - the open standard for extending AI agent capabilities. Use this skill when asked to create, write, or develop new skills for AI agents.

Teaches the agent how to create new Agent Skills - the open standard for extending AI agent capabilities. Use this skill when asked to create, write, or develop new skills for AI agents.

Use Codex/ChatGPT image analysis for one or many images with a custom prompt and structured output. Use when the user asks to analyze screenshots, inspect visuals, compare images, find UI moments, label extracted frames, or batch-process images with Codex. Automatically resizes images to Codex-friendly dimensions before analysis and supports one-image or many-image workflows.